# LTX 2.3 Trainer (V2) - Text-to-Audio API

> Traindt een LoRA voor tekst-naar-audio-generatie die een geluid of stijl uit je audioclips leert

Fine-tunet een LoRA uit een `.zip`-archief dat in `training_data_url` wordt opgegeven, zodat het model audio uit tekst kan genereren. Audio-specifieke opties zijn `audio_duration_seconds` (0.5 tot 60, standaard 5), `audio_normalize` en `audio_preserve_pitch`. De training gebruikt standaard 2000 stappen (100 tot 10000) met `rank` van 8 tot 128. De uitvoer bevat het LoRA-gewichtenbestand, een configuratiebestand en validatiepreviews.

- Model id: `ltx23-trainer-v2/t2a`
- Made by: Lightricks
- Category: Training
- Output: file
- Price: $0.0022 / step (cheapest run $4.40 (4400 API credits))
- Run: `POST https://api.doitong.com/v1/run/ltx23-trainer-v2/t2a`
- Quote: `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/t2a`
- Docs page: https://doitong.com/nl/developers/models/ltx23-trainer-v2/t2a

## Pricing

Price: **$0.0022 / step**. Billed per training step (`number_of_steps`).

The full example input below costs $4.40 = 4400 API credits (2000 steps × 2.2 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/ltx23-trainer-v2/t2a` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `training_data_url` |  | string | yes |  |  | URL naar een `.zip` met trainingsgegevens, georganiseerd volgens de geselecteerde trainingsmodus. Elk mediabestand kan een bijbehorend `.txt`-bijschrift met dezelfde basisnaam hebben. |
| `rank` |  | enum (integer) | no | `32` | `8`, `16`, `32`, `64`, `128` | LoRA-aanpassingsrang, waarbij een hogere instelling meer geheugengebruik inruilt voor grotere capaciteit. |
| `number_of_steps` |  | integer | no | `2000` | 100 – 10,000 | Totaal aantal trainingsstappen. |
| `learning_rate` |  | number | no | `0.0002` | 0.000001 – 1 | Leersnelheid voor optimalisatie. |
| `number_of_frames` |  | integer | no | `89` | 9 – 121 | Aantal frames per trainingssample. Delen door 8 moet rest 1 opleveren; voorbeelden zijn 1, 9, 17, 25, 33, 41, 49, 57, 65, 73, 81, 89, 97. |
| `frame_rate` |  | integer | no | `24` | 8 – 60 | Doelframerate van de trainingsvideo in frames per seconde. De native snelheid voor LTX-2.3 is 24. |
| `resolution` |  | enum (string) | no | `medium` | `low`, `medium`, `high` | Trainingsresolutie. Een hogere resolutie verhoogt de geheugenvereisten. |
| `aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Beeldverhouding voor training. |
| `trigger_phrase` |  | string | no | `` |  | Activeringszin voor de LoRA-stijl, ingevoegd aan het begin van bijschriften tijdens de training. |
| `auto_scale_input` |  | boolean | no | `false` |  | Automatische videoaanpassing aan de aangevraagde FPS en het aantal frames wanneer ingeschakeld; afbeeldingsdatasets blijven ongewijzigd. |
| `split_input_into_scenes` |  | boolean | no | `true` |  | Scènesplitsing voor video's die een duurdrempel overschrijden, ingeschakeld wanneer true. |
| `split_input_duration_threshold` |  | number | no | `30` | 1 – 60 | Trigger voor het splitsen van scènes, uitgedrukt als duur in seconden: alleen video's die langer zijn dan de drempel worden gesplitst. |
| `debug_dataset` |  | boolean | no | `false` |  | Inspectiemodus voor preprocessing om video's, afbeeldingen en bijschriften te controleren vóór een volledige trainingsrun. Inschakelen laat de trainer de verwerkte trainingsdataset teruggeven in een downloadbaar archief voor handmatige controle. |
| `audio_normalize` |  | boolean | no | `true` |  | Normalisatie van audiopieken om consistente niveaus in de hele dataset te behouden. |
| `audio_preserve_pitch` |  | boolean | no | `true` |  | Behoud van toonhoogte bij het passend maken van de audioduur, in plaats van afknippen of opvullen. |
| `audio_duration_seconds` |  | number | no | `5` | 0.5 – 60 | Audi duurbucket, opgegeven als doellengte in seconden: clips die deze overschrijden worden passend afgeknipt, terwijl clips die de lengte niet kunnen vullen worden overgeslagen. |
| `validation` |  | array of object {prompt} | no | `[]` | ≤ 2 items | Lijst met validatieprompts die wordt gebruikt om voor elke entry audio te genereren. |
| `validation[].prompt` |  | string | yes |  |  | Prompt die tijdens validatie wordt gebruikt. |
| `validation_negative_prompt` |  | string | no | `blurry, out of focus, overexposed, underexposed, low contrast, washed out colors, excessive noise, grainy texture, poor lighting, flickering, motion blur, distorted proportions, unnatural skin tones, deformed facial features, asymmetrical face, missing facial features, extra limbs, disfigured hands, wrong hand count, artifacts around text, inconsistent perspective, camera shake, incorrect depth of field, background too sharp, background clutter, distracting reflections, harsh shadows, inconsistent lighting direction, color banding, cartoonish rendering, 3D CGI look, unrealistic materials, uncanny valley effect, incorrect ethnicity, wrong gender, exaggerated expressions, wrong gaze direction, mismatched lip sync, silent or muted audio, distorted voice, robotic voice, echo, background noise, off-sync audio, incorrect dialogue, added dialogue, repetitive speech, jittery movement, awkward pauses, incorrect timing, unnatural transitions, inconsistent framing, tilted camera, flat lighting, inconsistent tone, cinematic oversaturation, stylized filters, or AI artifacts.` |  | Negatieve prompt die tijdens validatie wordt toegepast, met een proces in één fase. Omdat dit proces de gedistilleerde productie-inferentie met twee fasen benadert, verschillen de begeleiding en previewkwaliteit van de uiteindelijke resultaten. |
| `validation_number_of_frames` |  | integer | no | `89` | 9 – 121 | Aantal frames voor elke validatievideo. |
| `validation_frame_rate` |  | integer | no | `24` | 8 – 60 | Doelframerate voor validatievideo's, in frames per seconde; LTX-2.3 draait native op 24. |
| `validation_resolution` |  | enum (string) | no | `high` | `low`, `medium`, `high` | Resolutie die tijdens validatie wordt gebruikt. |
| `validation_aspect_ratio` |  | enum (string) | no | `1:1` | `16:9`, `1:1`, `9:16` | Beeldverhouding die tijdens validatie wordt gebruikt. |
| `stg_scale` |  | number | no | `1` | 0 – 3 | Schaal van Spatio-Temporal Guidance (STG), waarbij 1.0 wordt aanbevolen en 0.0 STG uitschakelt. |

## Example input

Required parameters only:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

A fuller example:

```json
{
  "training_data_url": "https://example.com/your-file.zip"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ltx23-trainer-v2/t2a?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "training_data_url": "https://example.com/your-file.zip"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/ltx23-trainer-v2/t2a?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "training_data_url": "https://example.com/your-file.zip"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "training_data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/ltx23-trainer-v2/t2a", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "ltx23-trainer-v2/t2a",
      "input": {
        "training_data_url": "https://example.com/your-file.zip"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ltx23-trainer-v2/t2a",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 4400,
    "usd": "4.40",
    "charged": 4400,
    "refunded": 0
  },
  "input": {
    "training_data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "lora_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "config_file": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    },
    "debug_dataset": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `video` | object {url, content_type, file_name, file_size} \| null | Gecombineerde videopreview uit de validatie, indien beschikbaar voor endpoints die video produceren. |
| `audio` | object {url, content_type, file_name, file_size} \| null | Gecombineerde audio uit de validatie, als preview geleverd wanneer beschikbaar voor deze audio-only-routes: /audio-inpaint, /audio-extend-suffix, /audio-extend-prefix, /t2a, /a2a en /v2a. |
| `lora_file` | object {url, content_type, file_name, file_size} | URL naar getrainde LoRA-gewichten in .safetensors-formaat. |
| `config_file` | object {url, content_type, file_name, file_size} | Configuratie voor het instellen van het inferentie-endpoint. |
| `debug_dataset` | object {url, content_type, file_name, file_size} \| null | Debug-uitvoer die beschikbaar is wanneer `debug_dataset` is ingeschakeld: een downloadbaar archief met de trainingsgegevens na preprocessing. |

## Related models

- [LTX 2.3 Trainer (V2) - Audio Inpainting](https://doitong.com/developers/models/ltx23-trainer-v2/audio-inpaint.md) (`ltx23-trainer-v2/audio-inpaint`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/av2av.md) (`ltx23-trainer-v2/ic-lora/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio+Video Reference Transformation](https://doitong.com/developers/models/ltx23-trainer-v2/av2av.md) (`ltx23-trainer-v2/av2av`): $0.0068 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio](https://doitong.com/developers/models/ltx23-trainer-v2/a2a.md) (`ltx23-trainer-v2/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Audio IC-LoRA](https://doitong.com/developers/models/ltx23-trainer-v2/ic-lora/a2a.md) (`ltx23-trainer-v2/ic-lora/a2a`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Audio-to-Video](https://doitong.com/developers/models/ltx23-trainer-v2/a2v.md) (`ltx23-trainer-v2/a2v`): $0.006 / step
- [LTX 2.3 Trainer (V2) - Backward Audio Extension](https://doitong.com/developers/models/ltx23-trainer-v2/audio-extend-suffix.md) (`ltx23-trainer-v2/audio-extend-suffix`): $0.0023 / step
- [LTX 2.3 Trainer (V2) - Backward Video Extension](https://doitong.com/developers/models/ltx23-trainer-v2/extend-suffix.md) (`ltx23-trainer-v2/extend-suffix`): $0.0061 / step

## Links

- HTML page: https://doitong.com/developers/models/ltx23-trainer-v2/t2a
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=ltx23-trainer-v2/t2a
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/ltx23-trainer-v2/t2a